Skip to Content

An Amazing AI Advance Makes Google’s Smart Butler Sound Way Better

October 5, 2017

You can thank DeepMind for the slick new voice that emanates from Google’s Home speaker and Assistant app.

This time last year, Google’s London-based AI division announced a new way to synthesize speech. Its software, called WaveNet, tore up the regular rule book for generating human-like voices: instead of stitching together chunks of sound, which ends up creating the clunky robotic voices we’re used to, it generated a whole audio waveform from scratch, one sample after the next. The result was far smoother, with more natural intonations than other speech synthesis approaches.

But there was a hitch: the software took one second to generate 0.02 seconds of audio, making it impractical for use in consumer products. DeepMind said it wouldn’t be used in any of Google’s software for some time, meaning that the clunky old-style voices had to remain.

But over the last 12 months, things have changed. DeepMind now reports that it’s managed to speed up the algorithm by a factor of 1,000, so it can create 20 seconds of audio in one second of compute time. (It does that while actually creating higher-fidelity audio than the old algorithm.) That’s a huge leap, and it has made it possible to run the software on Google’s AI cloud system.

In fact, that’s what is now used to create all the speech uttered by Google’s Assistant AI (which, incidentally, now comes in both male and females versions) on phones and smart speakers.

You can hear an example of old-style non-WaveNet speech synthesis here and the same sentence uttered by the new, fast algorithm here. The difference is pretty stark.

Sadly, DeepMind hasn’t yet published details about how it managed to create the ultra-efficient version of WaveNet, but it says that it plans to in the near future.

Deep Dive


Embracing CX in the metaverse

More than just meeting customers where they are, the metaverse offers opportunities to transform customer experience.

Identity protection is key to metaverse innovation

As immersive experiences in the metaverse become more sophisticated, so does the threat landscape.

The modern enterprise imaging and data value chain

For both patients and providers, intelligent, interoperable, and open workflow solutions will make all the difference.

Scientists have created synthetic mouse embryos with developed brains

The stem-cell-derived embryos could shed new light on the earliest stages of human pregnancy.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at with a list of newsletters you’d like to receive.